aimath_basic.h File Reference

Basic data-type independent math operations. More...

Go to the source code of this file.

Functions
void	print_aitensor (const aitensor_t *tensor)
	Printing a tensor to console. More...
void	print_aiscalar (const void *scalar, const aimath_dtype_t *dtype)
	Printing a scalar to console. More...
void	aimath_transpose_vector (aitensor_t *vector)
	Transposes a vector. More...
uint32_t	aimath_tensor_elements (const aitensor_t *tensor)
	Calculates the number of elements in a tensor. More...
uint32_t	aimath_sizeof_dtype (const aimath_dtype_t *dtype)
	Returns the size of one value in the given data type in bytes. More...
uint32_t	aimath_sizeof_tensor_data (const aitensor_t *tensor)
	Returns size of the data array of the tensor in bytes. More...
uint32_t	aimath_sizeof_tensor_params (const aitensor_t *tensor)
	Returns size of the aitensor.tensor_params for the data type of the tensor. More...
uint32_t	aimath_sizeof_tensor (const aitensor_t *tensor)
	Returns size of tensor in bytes. More...

Detailed Description

Basic data-type independent math operations.

Version

2.2.0

Copyright

Copyright (C) 2020-2023 Fraunhofer Institute for Microelectronic Circuits and Systems. All rights reserved.

AIfES is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License along with this program. If not, see https://www.gnu.org/licenses/.

Function Documentation

aimath_sizeof_dtype()

uint32_t aimath_sizeof_dtype

(

const aimath_dtype_t *

dtype

)

Returns the size of one value in the given data type in bytes.

Parameters

*dtype

The data type to get the size of

Returns

Size of one value in the given data type in bytes

aimath_sizeof_tensor()

uint32_t aimath_sizeof_tensor

(

const aitensor_t *

tensor

)

Returns size of tensor in bytes.

The size is calculated by:

sizeof(aitensor_t) + aimath_sizeof_tensor_data(tensor) + aimath_sizeof_tensor_params(tensor) 

Parameters

*tensor

The tensor to get the size of

Returns

Size of tensor in bytes

aimath_sizeof_tensor_data()

uint32_t aimath_sizeof_tensor_data

(

const aitensor_t *

tensor

)

Returns size of the data array of the tensor in bytes.

The size is calculated by:

aimath_tensor_elements(tensor) * aimath_sizeof_dtype(tensor.dtype) 

Parameters

*tensor

The tensor to get the data size of

Returns

Size of tensor data in bytes

aimath_sizeof_tensor_params()

uint32_t aimath_sizeof_tensor_params

(

const aitensor_t *

tensor

)

Returns size of the aitensor.tensor_params for the data type of the tensor.

Parameters

*tensor

The tensor to get the parameters size of

Returns

Size of tensor parameters in bytes

aimath_tensor_elements()

uint32_t aimath_tensor_elements

(

const aitensor_t *

tensor

)

Calculates the number of elements in a tensor.

Parameters

*tensor

The tensor to count the elements of

Returns

Number of elements in tensor

aimath_transpose_vector()

void aimath_transpose_vector

(

aitensor_t *

vector

)

Transposes a vector.

\[ vector \leftarrow vector^T \]

Make sure that the given tensor is a vector (with shape [1 x N] or [N x 1])

Parameters

*vector

The vector to transpose (2D tensor of shape [1 x N] or [N x 1])

print_aiscalar()

void print_aiscalar	(	const void *	scalar,
		const aimath_dtype_t *	dtype
	)

Printing a scalar to console.

Calls the corresponding print function of the used aimath_dtype.

Example:

aiscalar_f32_t scalar = 42.0f;
 
print_aiscalar(&scalar, aif32);

Parameters

*scalar	The scalar to print.
*dtype	The data type of the scalar

print_aitensor()

void print_aitensor

(

const aitensor_t *

tensor

)

Printing a tensor to console.

Calls the corresponding print function of the used aimath_dtype.

Example:

uint16_t tensor_shape[2] = {2, 3};
float tensor_data[2*3] = {1.0f, 2.0f, 3.0f,
                          4.0f, 5.0f, 6.0f};
aitensor_t tensor = AITENSOR_2D_F32(tensor_shape, tensor_data);
 
print_aitensor(&tensor);

Parameters

*tensor

The tensor to print.